Supercharge your AI with FRED Categories. Map out every economic data structure.
Works with every AI agent you already use
…and any MCP-compatible client








Connect to your AI in seconds.
FRED Categories helps you map out the entire economic data taxonomy. Start anywhere—from Money & Banking to Prices—and drill down through thousands of potential series.
It lets your agent discover which categories exist, what dimensions are available for filtering, and ultimately, find the exact time-series indicator you need.
What your AI can do
Get category
Retrieves details for a single, specific FRED category using its unique ID.
Get category children
Lists all the subcategories that fall under a primary category ID to help you map out the full hierarchy.
Get category series
Gathers lists of actual data series within a known category, allowing filters by frequency and units.
View the primary, root categories of economic data like National Accounts or Prices.
Navigate from a broad category to its specific child sections to narrow your focus.
Check the available tags for any given category, telling you what filters (like frequency or unit) apply before running a query.
Pull lists of actual time-series indicators within a category, applying filters for units and relevance.
Ask an AI about this
Compatible AI Apps
OAuth 2.0 CompatibleWaiting for input…
FRED Categories — 4 Tools
These four tools allow your agent to systematically explore the full hierarchy of economic data available in the FRED repository.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using FRED Categories — Economic Data Taxonomy on VinkiusGet Category
Retrieves details for a single, specific FRED category using its unique ID.
Get Category Children
Lists all the subcategories that fall under a primary category ID to help you map...
Get Category Series
Gathers lists of actual data series within a known category, allowing filters by...
Get Category Tags
Returns the available metadata tags for any given category, helping you understand...
Connect to your AI in seconds. Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with FRED Categories — Economic Data Taxonomy, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by FRED. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 4 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
It’s a nightmare trying to map out massive datasets manually.
Right now, figuring out what data FRED has means clicking into one category, then checking its sub-categories, and repeating that process dozens of times. You have to jump between tabs just to see if the necessary dimensions—like 'Real' or 'Nominal'—are even available for filtering.
With this MCP, your agent maps the entire structure in minutes. It quickly outlines all major top-level domains and then drills down through every child category path you need. The output is a clean, complete taxonomy map showing exactly where to look.
get_category_series: Pinpointing the exact data needed.
The biggest time sink is going from 'I know I need inflation data' to 'What series ID should I use?' You waste time cross-referencing multiple guides and looking for that specific indicator in a massive list.
This MCP solves it by letting your agent narrow the search. After mapping the category path, you simply ask for the series within that domain, filtering instantly by unit or frequency. The data structure is finally manageable.
What your AI can actually do with this
Need to figure out what data FRED even has? This MCP acts like an expert librarian, allowing your AI client to navigate the massive tree of economic indicators. You don't have to click through eight different menus just to see if a category exists or what tags it supports. Your agent first gets a high-level view by mapping out all major top-level domains.
Once you zero in on an area—say, employment data—it then shows the subcategories within that domain. You can even run a check to see exactly which dimensions apply, like 'Quarterly' or 'Urban,' before you pull any results. This deep structural insight is invaluable for research because it lets your agent find all available series and filter them instantly using Vinkius's catalog framework.
It turns a massive data dump into an actionable map.
019d759e-e282-7026-8660-91bd642ed82d Here's how it actually works
The bottom line is that your agent gets an entire, structured map of FRED's content library before it even tries to pull a single data point.
Start by mapping the root categories to define your general area of interest (e.g., Money & Banking).
Use this MCP to explore the child categories, drilling down until you isolate the specific sub-domain containing the data series you need.
Run a final check using available tags and then request the list of actual time-series indicators within that final category.
Who is this actually for?
Financial analysts and economic researchers who spend too much time clicking through complex government websites. It’s for anyone whose job requires understanding the full scope of available structured metadata.
Determines which set of indicators is relevant to a hypothesis by mapping out the entire data structure and filtering potential series.
Builds reusable, structured reports by identifying the correct category path and associated tags for consistent indicator retrieval across multiple projects.
Needs a complete inventory of potential time-series inputs to ensure no relevant data source is overlooked when building predictive models.
What Changes When You Connect
Stop guessing which indicator exists. By using get_category_tags, you check all available dimensions for a category first, so your agent knows exactly how to filter the results.
Don't waste time clicking through endless menus. Get_category_children lets you programmatically map out every single sub-domain beneath a major topic, giving you a complete structural overview.
Get data series lists instantly. When you know the category, get_category_series pulls all relevant indicators and allows filtering by frequency or units in one call.
Pinpoint your starting point. If you only know an indicator's general domain (like 'Prices'), get_category lets you jump right to that root ID without browsing.
Understand the data scope. You don't just see categories; you understand their limitations and available metadata using get_category_tags.
See it in action
A client needs a complete list of labor market indicators.
The analyst asks the agent for all employment data. The agent first uses get_category to confirm the main 'Population & Employment' ID, then calls get_category_children to map out sub-domains like 'Unemployment Rate.' Finally, it uses get_category_series to pull every relevant time series from that specific child category.
A student needs to compare multiple types of inflation data.
The student asks about price indices. The agent first checks the root categories using get_category, lands in 'Prices,' and then uses get_category_tags to see if they can filter by specific units (like CPI vs. PCE) before pulling any final series list.
A quant wants to build a model that incorporates multiple national accounts.
The agent maps the root categories using get_category, then systematically calls get_category_children for 'National Accounts' and 'Money & Banking.' It builds an inventory of potential data inputs without ever needing to see the actual series.
A developer needs a clean taxonomy structure for their app.
The agent uses get_category_children across several major domains to build a complete, structured JSON map. This allows them to design an entire data selection interface based on the true depth of FRED's offerings.
The honest tradeoffs
Searching by vague keywords
Telling your agent: 'Give me all things about money.' This is too broad and gives no structural guidance.
Start with get_category to identify the root ID (e.g., Money, Banking & Finance). Then use get_category_children to drill down into specific sub-sections for a targeted result.
Assuming all data is visible
Running a series list without checking filters, leading to incomplete or irrelevant results.
Always run get_category_tags first. This tells you the available dimensions (like 'Quarterly' or 'Inflation') so you can properly filter your request using get_category_series.
Skipping structural mapping
Jumping straight to a series ID without knowing its parent category, causing lookup failures.
Always use get_category and then get_category_children. This establishes the correct structural path (the parent ID) before you try to retrieve any specific data.
When It Fits, When It Doesn't
Use this MCP if your primary job is discovery, mapping structure, or understanding the breadth of available metadata. If you need to know what economic data exists and how it's organized, this is the tool. Don't use it if you already know the exact series ID and only need a single piece of data; in that case, a direct API call might be faster. Also, don't assume tags cover everything; always check get_category_children first to confirm the structural path.
Questions you might have
How do I find all top-level economic categories using get_category? +
You don't use it for the whole thing; you use get_category_children. This function starts at root (0) and maps out all major domains, like Money or Prices, so you know where to start looking.
What is the best way to filter results using get_category_tags? +
You use it after identifying a category. It returns the available tags for that specific category, letting your agent confirm which dimensions (e.g., 'quarterly' or 'urban') you can actually apply later.
If I know a general topic, how do I find all related data? (get_category) +
Use get_category to confirm the primary ID for that topic. This gives your agent the necessary starting point before it can map out the deeper children or series within that domain.
Does get_category_series give me data, or just a list of indicators? +
It provides a comprehensive list of potential time-series indicators. It gives you the metadata and IDs needed to pull the actual time-series data later.
What should I do if an ID is invalid when using get_category? +
The tool will return a specific error code indicating the ID does not exist. Always cross-reference any category ID you input with the official FRED documentation first.
Are there rate limits when I run multiple queries, such as running get_category_children followed by get_category_series? +
Yes. Usage follows FRED's published API guidelines. For deep data exploration across many categories, monitor your usage to stay within the allotted call limits.
If I run get_category_tags and receive an empty list, does that mean the category has no tags? +
It means there are currently no available dimension tags for that specific category. Try checking related parent categories or adjusting your search scope.
Do I need to worry about data formatting when using get_category_series? +
The tool provides structured JSON output. Your AI client receives clean, machine-readable records that make processing the time series straightforward for downstream analysis.
How is FRED organized? +
FRED uses a hierarchical tree of categories. The root (ID 0) branches into 8 domains like Money & Banking, Employment, and Prices. Each domain subdivides into hundreds of subcategories, each containing related series. Start from root and drill down to discover data.
We've already built the connector for FRED Categories. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 4 tools are live and waiting.
You're up and running in seconds.
Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.